Abstract—In this paper, a carbon price forecasting system is
proposed to quickly and accurately predict the carbon price for
participants. The data including the carbon trading price, oil
price, coal price and gas price are first calculated and the data
clusters are embedded in the Excel Database. Based on the
Radial Basis Function Network (RBFN) and Ant Colony
Optimization (ACO), an Ant-Based Radial Basis Function
Network (ARBFN) is constructed in the searching process. The
optimal parameters obtained from the ACO enable the learning
rate parameters to regulate and improve the predicting errors
during the training process. By linking the ARBFN and Excel
database, the training stages of the ARBFN retrieve the input
data from the Excel Database so that the efficiency and
accuracy of the predicting system can be analyzed. A
comparison of the Back-propagation Neural Network (BPN),
Radial Basis function (RBFN), Probability Neural Network
(PNN) and the ARBFN show that the converging solution is
obtained by the prediction process. Simulation results will
provide an accurate and real-time method for participants to
forecast carbon price and raise the market competition in a
carbon trading market.
Index Terms—Carbon trading market, radial basis function network, ant colony optimization, carbon price.
Ming-Tang Tsai and Yu-Teing Kuo are with the Department of Electrical Engineering, Cheng-Shiu University, Kaohsiung, Taiwan, R.O.C (e-mail: firstname.lastname@example.org).
Cite:Ming-Tang Tsai and Yu-Teing Kuo, "A Forecasting System of Carbon Price in the Carbon Trading Markets Using Artificial Neural Network," International Journal of Environmental Science and Development vol. 4, no. 2, pp. 163-167, 2013.